{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T17:48:38Z","timestamp":1768499318895,"version":"3.49.0"},"reference-count":42,"publisher":"China Science Publishing & Media Ltd.","issue":"4","content-domain":{"domain":["engine.scichina.com"],"crossmark-restriction":false},"short-container-title":["DI"],"published-print":{"date-parts":[[2025,12,1]]},"DOI":"10.3724\/2096-7004.di.2025.0025","type":"journal-article","created":{"date-parts":[[2025,4,30]],"date-time":"2025-04-30T05:11:33Z","timestamp":1745989893000},"page":"1085-1107","update-policy":"https:\/\/doi.org\/10.1360\/scp-crossmark-policy-page","source":"Crossref","is-referenced-by-count":0,"title":["MAPS: A Multi-task Framework with Anchor Point Sampling for Zero-shot Entity Linking"],"prefix":"10.3724","volume":"7","author":[{"given":"Chao","family":"Chen","sequence":"first","affiliation":[]},{"given":"Pengfei","family":"Luo","sequence":"additional","affiliation":[]},{"given":"Changkai","family":"Feng","sequence":"additional","affiliation":[]},{"given":"Tian","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Wenbin","family":"Jiang","sequence":"additional","affiliation":[]},{"given":"Tong","family":"Xu","sequence":"additional","affiliation":[]}],"member":"2026","published-online":{"date-parts":[[2025,3,1]]},"reference":[{"key":"","unstructured":"Sun K., Zhang R., Mensah S., Mao Y., and Liu X., \u201cA transformational biencoder with in-domain negative sampling for zero-shot entity linking,\u201d in ACL (Findings). Association for Computational Linguistics, 2022, pp. 1449-1458."},{"key":"","unstructured":"Yang J., Wang D., Zhou W., Qian W., Wang X., Han J., and Hu S., \u201cEntity and relation matching consensus for entity alignment,\u201d in CIKM \u201821: The 30 th  ACM International Conference on Information and Knowledge Management, Virtual Event, Queensland, Australia, November 1\u20135, 2021, Demartini G., Zuccon G., Culpepper J. S., Huang Z., and Tong H., Eds. ACM, pp. 2331-2341."},{"key":"","unstructured":"Luo P., Xu T., Wu S., Zhu C., Xu L., and Chen E., \u201cMulti-grained multimodal interaction network for entity linking,\u201d in Proceedings of the 29 th  ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2023, pp. 1583-1594."},{"key":"","unstructured":"Lan Y., Wang S., and Jiang J., \u201cKnowledge base question answering with topic units,\u201d in Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, IJCAI 2019, Macao, China, August 10\u201316, 2019, Kraus S., Ed. ijcai.org, pp. 5046-5052."},{"key":"","unstructured":"Chen H., \u201cLarge knowledge model: Perspectives and challenges,\u201d Data Intelligence, vol. 6, no. 3, pp. 587-620, Aug. 2024."},{"key":"","unstructured":"Mart\u00ednez-Rodr\u00edguez J., Hogan A., and L\u00f3pez-Ar\u00e9valo I., \u201cInformation extraction meets the semantic web: A survey,\u201d Semantic Web, vol. 11, no. 2, pp. 255-335, 2020."},{"key":"","unstructured":"Parravicini A., Patra R., Bartolini D. B., and Santambrogio M. D., \u201cFast and accurate entity linking via graph embedding,\u201d in Proceedings of the 2 nd  Joint International Workshop on Graph Data Management Experiences & Systems (GRADES) and Network Data Analytics (NDA), Amsterdam, The Netherlands, 30 June 2019, Arora A., Bhattacharya A., and Fletcher G. H. L., Eds. ACM, pp. 10:1-10:9."},{"key":"","unstructured":"Sui X., Zhang Y., Song K., Zhou B., Zhao G., Wei X., and Yuan X., \u201cImproving zero-shot entity linking candidate generation with ultra-fine entity type information,\u201d in COLING. International Committee on Computational Linguistics (2022), pp. 2429-2437."},{"key":"","unstructured":"Ristoski P., Lin Z., and Zhou Q., \u201cKG-ZESHEL: knowledge graph-enhanced zero-shot entity linking,\u201d in K-CAP. ACM (2021), pp. 49-56."},{"key":"","unstructured":"Ratinov L., Roth D., Downey D., and Anderson M., \u201cLocal and global algorithms for disambiguation to wikipedia,\u201d in ACL. The Association for Computer Linguistics (2011), pp. 1375-1384."},{"key":"","unstructured":"Hoffart J., Yosef M. A., Bordino I., F\u00fcrstenau H., Pinkal M., Spaniol M., Taneva B., Thater S., and Weikum G., \u201cRobust disambiguation of named entities in text,\u201d in EMNLP. ACL (2011), pp. 782-792."},{"key":"","unstructured":"Ganea O. and Hofmann T., \u201cDeep joint entity disambiguation with local neural attention,\u201d in EMNLP. Association for Computational Linguistics (2017), pp. 2619-2629."},{"key":"","unstructured":"Zhang W. and Stratos K., \u201cUnderstanding hard negatives in noise contrastive estimation,\u201d in NAACL-HLT. Association for Computational Linguistics (2021), pp. 1090-1101."},{"key":"","unstructured":"Logeswaran L., Chang M., Lee K., Toutanova K., Devlin J., and Lee H., \u201cZeroshot entity linking by reading entity descriptions,\u201d in ACL (1). Association for Computational Linguistics (2019), pp. 3449-3460."},{"key":"","unstructured":"Zhang W., Hua W., and Stratos K., \u201cEntqa: Entity linking as question answering,\u201d in ICLR. OpenReview.net (2022)."},{"key":"","unstructured":"Kolitsas N., Ganea O., and Hofmann T., \u201cEnd-to-end neural entity linking,\u201d in CoNLL. Association for Computational Linguistics (2018), pp. 519-529."},{"key":"","unstructured":"Le P. and Titov I., \u201cImproving entity linking by modeling latent relations between mentions,\u201d in ACL (1). Association for Computational Linguistics (2018), pp. 1595-1604."},{"key":"","unstructured":"Wu L., Petroni F., Josifoski M., Riedel S., and Zettlemoyer L., \u201cScalable zero-shot entity linking with dense entity retrieval,\u201d in EMNLP (1). Association for Computational Linguistics (2020), pp. 6397-6407."},{"key":"","unstructured":"Wu T., Bai X., Guo W., Liu W., Li S., and Yang Y., \u201cModeling fine-grained information via knowledge-aware hierarchical graph for zero-shot entity retrieval,\u201d in Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining, 2023, pp. 1021-1029."},{"key":"","unstructured":"Choi E., Levy O., Choi Y., and Zettlemoyer L., \u201cUltra-fine entity typing,\u201d in ACL (1). Association for Computational Linguistics (2018), pp. 87-96."},{"key":"","unstructured":"Dai H., Song Y., and Wang H., \u201cUltra-fine entity typing with weak supervision from a masked language model,\u201d in ACL\/IJCNLP (1). Association for Computational Linguistics, 2021, pp. 1790-1799."},{"key":"","unstructured":"Ma X., Zhao L., Huang G., Wang Z., Hu Z., Zhu X., and Gai K., \u201cEntire space multitask model: An effective approach for estimating post-click conversion rate,\u201d in SIGIR. ACM (2018), pp. 1137-1140."},{"key":"","unstructured":"Ma J., Zhao Z., Yi X., Chen J., Hong L., and Chi E. H., \u201cModeling task relationships in multi-task learning with multi-gate mixture-of-experts,\u201d in KDD. ACM (2018), pp. 1930-1939."},{"key":"","unstructured":"Tang H., Liu J., Zhao M., and Gong X., \u201cProgressive layered extraction (PLE): A novel multi-task learning (MTL) model for personalized recommendations,\u201d in RecSys. ACM (2020), pp. 269-278."},{"key":"","unstructured":"Yao Z., Cao L., and Pan H., \u201cZero-shot entity linking with efficient long range sequence modeling,\u201d vol. EMNLP 2020, pp. 2517-2522, 2020."},{"key":"","unstructured":"Ma X., Jiang Y., Bach N., Wang T., Huang Z., Huang F., and Lu W., \u201cMuver: Improving first-stage entity retrieval with multi-view entity representations,\u201d in Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, EMNLP 2021, Virtual Event\/Punta Cana, Dominican Republic, 7\u201311 November, 2021, Moens M., Huang X., Specia L., and Yih S. W., Eds. Association for Computational Linguistics, pp. 2617-2624."},{"key":"","unstructured":"Zuo X., Liang H., Jing N., Zeng S., Fang Z., and Luo Y., \u201cType-enriched hierarchical contrastive strategy for fine-grained entity typing,\u201d in COLING. International Committee on Computational Linguistics (2022), pp. 2405-2417."},{"key":"","unstructured":"Ding N., Chen Y., Han X., Xu G., Wang X., Xie P., Zheng H., Liu Z., Li J., and Kim H., \u201cPrompt-learning for fine-grained entity typing,\u201d pp. 6888\u20136901, 2022."},{"key":"","unstructured":"Chen W., Zhao L., Luo P., Xu T., Zheng Y., and Chen E., \u201cHeproto: A hierarchical enhancing protonet based on multi-task learning for few-shot named entity recognition,\u201d in Proceedings of the 32 nd  ACM International Conference on Information and Knowledge Management, 2023, pp. 296-305."},{"key":"","unstructured":"Giunchiglia E. and Lukasiewicz T., \u201cCoherent hierarchical multi-label classification networks,\u201d in NeurIPS, 2020."},{"key":"","unstructured":"Lester B., Al-Rfou R., and Constant N., \u201cThe power of scale for parameter-efficient prompt tuning,\u201d in EMNLP (1). Association for Computational Linguistics (2021), pp. 3045-3059."},{"key":"","unstructured":"Li X. L. and Liang P., \u201cPrefix-tuning: Optimizing continuous prompts for generation,\u201d pp. 4582\u20134597, 2021."},{"key":"","unstructured":"Liang X., Yao L., Liu X., and Zhou Y., \u201cTripartite: Tackle noisy labels by a more precise partition,\u201d CoRR, vol. abs\/2202.09579, 2022."},{"key":"","unstructured":"Lerer A., Wu L., Shen J., Lacroix T., Wehrstedt L., Bose A., and Peysakhovich A., \u201cPytorch-biggraph: A large scale graph embedding system,\u201d 2019."},{"key":"","unstructured":"Kendall A., Gal Y., and Cipolla R., \u201cMulti-task learning using uncertainty to weigh losses for scene geometry and semantics,\u201d in CVPR. Computer Vision Foundation \/ IEEE Computer Society (2018), pp. 7482-7491."},{"key":"","unstructured":"Lin X., Chen H., Pei C., Sun F., Xiao X., Sun H., Zhang Y., Ou W., and Jiang P., \u201cA pareto-efficient algorithm for multiple objective optimization in e-commerce recommendation,\u201d in RecSys. ACM (2019), pp. 20-28."},{"key":"","unstructured":"Liu S., Johns E., and Davison A. J., \u201cEnd-to-end multi-task learning with attention,\u201d in CVPR. Computer Vision Foundation\/IEEE (2019), pp. 1871-1880."},{"key":"","unstructured":"Chen Z., Badrinarayanan V., Lee C., and Rabinovich A., \u201cGradnorm: Gradient normalization for adaptive loss balancing in deep multitask networks,\u201d in ICML, ser. Proceedings of Machine Learning Research, vol. 80. PMLR (2018), pp. 793-802."},{"key":"","unstructured":"Devlin J., Chang M., Lee K., and Toutanova K., \u201cBERT: pre-training of deep bidirectional transformers for language understanding,\u201d pp. 4171\u20134186, 2019."},{"key":"","unstructured":"Loshchilov I. and Hutter F., \u201cFixing weight decay regularization in adam,\u201d CoRR, vol. abs\/1711.05101, 2017."},{"key":"","unstructured":"Robertson S. E. and Zaragoza H., \u201cThe probabilistic relevance framework: BM25 and beyond,\u201d Found. Trends Inf. Retr., vol. 3, no. 4, pp. 333-389, 2009."},{"key":"","unstructured":"Wiatrak M., Arvaniti E., Brayne A., Vetterle J., and Sim A., \u201cProxy-based zero-shot entity linking by effective candidate retrieval,\u201d arXiv preprint arXiv: 2301.13318, 2023."}],"container-title":["Data Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.sciengine.com\/doi\/pdf\/1D68C39F51CE4E2E9BCB68DBAAD809A8","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.sciengine.com\/doi\/10.3724\/2096-7004.di.2025.0025","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.sciengine.com\/doi\/pdf\/1D68C39F51CE4E2E9BCB68DBAAD809A8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T03:16:12Z","timestamp":1768446972000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.sciengine.com\/doi\/10.3724\/2096-7004.di.2025.0025"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,1]]},"references-count":42,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2025,3,1]]},"published-print":{"date-parts":[[2025,12,1]]}},"URL":"https:\/\/doi.org\/10.3724\/2096-7004.di.2025.0025","relation":{},"ISSN":["2096-7004"],"issn-type":[{"value":"2096-7004","type":"print"}],"subject":[],"published":{"date-parts":[[2025,3,1]]}}}